PyPI / crates.io / RubyGems / Go index / NuGet
ucci-router 0.1.1(opens the publisher's site in a new tab)
UCCI: calibrated uncertainty for cost-optimal LLM cascade routing (token-margin signal, isotonic calibration, constrained threshold selection)
AI
Stories tagged ai.
PyPI / crates.io / RubyGems / Go index / NuGet
spec-probe 0.1.9(opens the publisher's site in a new tab)
Verify C/C++ modules implement functional requirements from spec (LangGraph + LLM)
PyPI / crates.io / RubyGems / Go index / NuGet
scrapefold 0.9.2(opens the publisher's site in a new tab)
Unified interface for web scraping engines — site to markdown with stealth, JS rendering, and LLM-ready output.
PyPI / crates.io / RubyGems / Go index / NuGet
mlia-converters-pytorch 0.1.1(opens the publisher's site in a new tab)
ML Inference Advisor PyTorch Converter Plugin
PyPI / crates.io / RubyGems / Go index / NuGet
fastbrowse 0.5.4(opens the publisher's site in a new tab)
A browser agent that picks instead of generating: Jev chooses, an LLM reads and plans, code verifies.
PyPI / crates.io / RubyGems / Go index / NuGet
mlia-ethos-u 0.1.0(opens the publisher's site in a new tab)
ML Inference Advisor Ethos Plugin
PyPI / crates.io / RubyGems / Go index / NuGet
gorget 0.5.0(opens the publisher's site in a new tab)
Security scanners for LLM prompts and responses: prompt injection, PII, secrets, toxicity and more. A maintained continuation of LLM Guard.
PyPI / crates.io / RubyGems / Go index / NuGet
hyperextract 0.10.4(opens the publisher's site in a new tab)
An intelligent, LLM-powered knowledge extraction and evolution framework with semantic search capabilities
PyPI / crates.io / RubyGems / Go index / NuGet
tfp-nightly 0.26.0.dev20260925(opens the publisher's site in a new tab)
Probabilistic modeling and statistical inference in TensorFlow
PyPI / crates.io / RubyGems / Go index / NuGet
nonebot-plugin-aigf-master 2.0.0b2(opens the publisher's site in a new tab)
群聊特化LLM聊天机器人（增强版），具有记忆、表情包、跨插件调用、跨bot通信与跨适配器支持
PyPI / crates.io / RubyGems / Go index / NuGet
llm-commonplace 0.2.0(opens the publisher's site in a new tab)
The theory of LLM wikis, running as one. A framework for agent-operated knowledge: typed, linked, review-gated markdown your agents execute.
PyPI / crates.io / RubyGems / Go index / NuGet
pinneapple 0.6.0(opens the publisher's site in a new tab)
PINNeAPPle: Physics-Informed Neural Networks platform — PDE problem design, PINN/operator/GNN models, UQ, digital twins, meta-learning, active learning, validation, and REST serving.
PyPI / crates.io / RubyGems / Go index / NuGet
mlia 0.12.2(opens the publisher's site in a new tab)
ML Inference Advisor
PyPI / crates.io / RubyGems / Go index / NuGet
piper-kernels 0.7.5(opens the publisher's site in a new tab)
Reusable PyTorch inference operators and Triton kernels.
PyPI / crates.io / RubyGems / Go index / NuGet
sphinx-llm-friendly 0.5.1(opens the publisher's site in a new tab)
Sphinx extension to make documentation LLM-friendly
PyPI / crates.io / RubyGems / Go index / NuGet
physai 5.1.0
Multi-backend Physics-Informed Neural Network (PINN) framework for solving, animating, and cross-validating ODEs/PDEs, with 50+ built-in equations, SDF-based geometry/CSG, and automatic architecture selection
PyPI / crates.io / RubyGems / Go index / NuGet
goldilocks-core 0.1.1(opens the publisher's site in a new tab)
Materials machine learning tools for recommending DFT calculation inputs.
Mint — Technology / AI
Anthropic’s new AI system lets lab machines talk to each other and run experiments(opens the publisher's site in a new tab)
Anthropic's Model Hardware Standard (MHS) lets different laboratory instruments communicate and work together through AI agents. The system can help automate experiments by enabling AI to control robotic arms, liquid-handling machines and other lab equipment.
TNW
Trump and House Speaker Mike Johnson will reportedly meet tech CEOs on AI on 29 September(opens the publisher's site in a new tab)
US President Donald Trump and House Speaker Mike Johnson will meet tech chief executives to discuss artificial intelligence on Tuesday, 29 September, Axios reported the plans on Thursday, citing a source familiar with them. A source also confirmed the date to Reuters, while ABC News said multiple…
PyPI / crates.io / RubyGems / Go index / NuGet
power-loop 6.32.0(opens the publisher's site in a new tab)
Embeddable agent execution kernel — LLM loop, hooks, events, tools, dynamic sub-agents.
PyPI / crates.io / RubyGems / Go index / NuGet
timu 0.2.0(opens the publisher's site in a new tab)
A team of specialised LLM agents with role-scoped tools
PyPI / crates.io / RubyGems / Go index / NuGet
vit-xray 0.1.0(opens the publisher's site in a new tab)
Look inside any vision transformer backbone in one command.
PyPI / crates.io / RubyGems / Go index / NuGet
ellf-recipes-gpu 0.1.187(opens the publisher's site in a new tab)
GPU recipes for Ellf (spaCy curated transformers training & inference)
PyPI / crates.io / RubyGems / Go index / NuGet
cmdop-llm 0.1.19(opens the publisher's site in a new tab)
Framework-neutral multi-provider LLM transport and Pydantic AI agent harness.
PyPI / crates.io / RubyGems / Go index / NuGet
agentweave-router 0.7.1(opens the publisher's site in a new tab)
Pre-inference routing for tool-rich LLMs and multi-agent systems with MCP, A2A, LangGraph, AutoGen, policy-aware routing, recovery, and reproducible evaluation.
PyPI / crates.io / RubyGems / Go index / NuGet
geki-apipi 0.5.1(opens the publisher's site in a new tab)
ApiPi is a drop-in OpenAI Agents API. Point official clients at this gateway and bring your own model URL.
PyPI / crates.io / RubyGems / Go index / NuGet
traccia 0.1.30(opens the publisher's site in a new tab)
Production-ready distributed tracing SDK for AI agents and LLM applications
AI News (artificialintelligence-news.com)
The GPU Shortage Inside Your Own Infrastructure: Why AI Workloads Queue While Capacity Sits Idle(opens the publisher's site in a new tab)
GPU utilisation shows compute activity, not whether capacity is actually available. A GPU can report low utilisation while remaining fully allocated to one workload. This post explains why workloads queue beside idle-looking GPUs, how allocation, memory, placement, and application bottlenecks…
PyPI / crates.io / RubyGems / Go index / NuGet
flexposit 0.2.1(opens the publisher's site in a new tab)
FlexPosit: mixed-precision Posit quantization for LLMs, with matching accelerator RTL.
PyPI / crates.io / RubyGems / Go index / NuGet
cmdop-llm 0.1.18(opens the publisher's site in a new tab)
Framework-neutral multi-provider LLM transport and Pydantic AI agent harness.
PyPI / crates.io / RubyGems / Go index / NuGet
my-claude-code 7.44.0
Local multi-provider LLM proxy, model router and control plane for Claude Code, Codex, OpenCode, Gemini CLI and other AI coding agents: 57 providers, fallback routing, credential health, a native web-search tool proxy, and analytics with cost provenance
The Quantum Insider / Quantum Computing Report
Evaluating Quantum Generative Models on Real Satellite Radar(opens the publisher's site in a new tab)
Insider Brief PRESS RELEASE — IonQ researchers applied a quantum generative machine learning model to help detect changes in highly complex satellite image data. The results, detailed in a recently published paper, reveal that using quantum-based analysis shows promise for detecting and predicting…
PyPI / crates.io / RubyGems / Go index / NuGet
returnn 1.20260925.91950(opens the publisher's site in a new tab)
The RWTH extensible training framework for universal recurrent neural networks
PyPI / crates.io / RubyGems / Go index / NuGet
traigent 0.28.0(opens the publisher's site in a new tab)
Enterprise-grade LLM optimization platform with advanced analytics and AI-powered insights
PyPI / crates.io / RubyGems / Go index / NuGet
words2num2 0.3.3(opens the publisher's site in a new tab)
Rust-powered inverse of num2words2: parse spoken-form numbers back to numeric values across 100+ languages, optimized for ASR/LLM/speech.
PyPI / crates.io / RubyGems / Go index / NuGet
scrapefold 0.9.1(opens the publisher's site in a new tab)
Unified interface for web scraping engines — site to markdown with stealth, JS rendering, and LLM-ready output.
PyPI / crates.io / RubyGems / Go index / NuGet
nonebot-plugin-aigf-master 2.0.0b1(opens the publisher's site in a new tab)
群聊特化LLM聊天机器人（增强版），具有记忆、表情包、跨插件调用、跨bot通信与跨适配器支持
AI News (artificialintelligence-news.com)
How to Add AI to Legacy Software Without Rebuilding It(opens the publisher's site in a new tab)
Most companies running legacy software assume that adding artificial intelligence means starting over, and that assumption stops many projects before they begin. Rewriting a system that has supported the business for 15 years is expensive, risky, and rarely necessary. In most cases, AI can sit on…
Economic Times — Tech / Technology / Startups / ETTelecom
Australia steps up response to AI after OpenAI bot breaches health system database(opens the publisher's site in a new tab)
The incursion on one of the country's most used government agencies may prompt a tougher stance as Australia readies AI-specific laws starting in 2027, adding pressure to Australia-US relations already tested by Canberra's teen social media ban, tech policy experts said.
PyPI / crates.io / RubyGems / Go index / NuGet
typellm 0.1.6
Type-Safe Decoding for Autoregressive LLMs
PyPI / crates.io / RubyGems / Go index / NuGet
ucci-router 0.1.0
UCCI: calibrated uncertainty for cost-optimal LLM cascade routing (token-margin signal, isotonic calibration, constrained threshold selection)
PyPI / crates.io / RubyGems / Go index / NuGet
inference-models 0.39.0.dev20260925
The new inference engine for Computer Vision models
PyPI / crates.io / RubyGems / Go index / NuGet
tolokaforge 0.27.3
Tolokaforge - LLM Tool-Use Benchmarking Harness
YourStory
Akamai lands $11.6B cloud computing deal with Anthropic(opens the publisher's site in a new tab)
The seven-year cloud infrastructure deal will support' Anthropic's growing CPU workloads and involves total capital expenditures of around $5.5 billion.
PyPI / crates.io / RubyGems / Go index / NuGet
seren-workbench 2.0.1
MCP server for the Seren stack — the tool surface LLMs reach through.
PyPI / crates.io / RubyGems / Go index / NuGet
seren-memory 4.0.0
Three-tier LLM memory with consolidation for Seren. The right brain - episodic, time-tiered, dreaming the durable out of the fleeting. The Halls of Memory.
PyPI / crates.io / RubyGems / Go index / NuGet
nkululeko 1.11.5
Machine learning audio prediction experiments based on templates
PyPI / crates.io / RubyGems / Go index / NuGet
openai-agents-zambo 0.1.0
Zambo's 100+ tools for the OpenAI Agents SDK, with a verifiable receipt on every call.